Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.7
2.9
Journals
JMSE
Special Issues
Application of Sensing and Machine Learning to Underwater Acoustic
share announcement

Application of Sensing and Machine Learning to Underwater Acoustic

A special issue of Journal of Marine Science and Engineering (ISSN 2077-1312). This special issue belongs to the section "Ocean Engineering".

Deadline for manuscript submissions: closed (15 February 2023) | Viewed by 30390

Special Issue Editors

Dr. Tracianne B Neilsen

E-Mail Website
Guest Editor
Department of Physics and Astronomy, Brigham Young University, Provo, UT 84602, USA
Interests: underwater acoustics; acoustic source localization; inverse methods; machine learning applications in underwater acoustics
Dr. Haiqiang Niu

E-Mail Website
Guest Editor
Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China
Interests: normal wave mode separation based on compressed sensing; horizontal wavenumber estimation; target direction-of-arrival estimation; and underwater acoustic passive localization and inversion based on machine learning (deep learning)

Special Issue Information

Dear Colleagues,

The aim of this Special Issue is to promote and disseminate the latest research that focuses on machine learning applications in underwater acoustics. Papers that address applications of machine learning in all fields of underwater acoustics—including (but not limited to) active and passive sonar, imaging, tomography, communication, bioacoustics, source localization, seabed characterization, signal classification, propagation modeling, and environmental monitoring—are welcomed. A broad interpretation of what qualifies as “machine learning” is adopted for this Special Issue, which includes advanced signal processing and Bayesian approaches. This issue seeks to highlight how the rapid improvement of computational resources and development of new algorithms are advancing the development of robust machine learning approaches to solve significant challenges in the field of underwater acoustics.

Dr. Tracianne B Neilsen
Dr. Haiqiang Niu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Marine Science and Engineering is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • machine learning
  • deep learning
  • underwater acoustics
  • active sonar
  • passive sonar
  • sonar imaging
  • acoustical tomography
  • underwater communications
  • source localization
  • seabed characterization
  • signal classification
  • propagation modeling
  • bioacoustics
  • environmental monitoring

Published Papers (17 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

16 pages, 12389 KiB  
Article
A Side-Scan Sonar Image Synthesis Method Based on a Diffusion Model
by Zhiwei Yang, Jianhu Zhao, Hongmei Zhang, Yongcan Yu and Chao Huang
J. Mar. Sci. Eng. 2023, 11(6), 1103; https://doi.org/10.3390/jmse11061103 - 23 May 2023
Cited by 3 | Viewed by 1753
Abstract
The limited number and under-representation of side-scan sonar samples hinders the training of high-performance underwater object detection models. To address this issue, in this paper, we propose a diffusion model-based method to augment side-scan sonar image samples. First, the side-scan sonar image is [...] Read more.
The limited number and under-representation of side-scan sonar samples hinders the training of high-performance underwater object detection models. To address this issue, in this paper, we propose a diffusion model-based method to augment side-scan sonar image samples. First, the side-scan sonar image is transformed into Gaussian distributed random noise based on its a priori discriminant. Then, the Gaussian noise is modified step by step in the inverse process to reconstruct a new sample with the same distribution as the a priori data. To improve the sample generation speed, an accelerated encoder is introduced to reduce the model sampling time. Experiments show that our method can generate a large number of representative side-scan sonar images. The generated side-scan sonar shipwreck images are used to train an underwater shipwreck object detection model, which achieves a detection accuracy of 91.5% on a real side-scan sonar dataset. This exceeds the detection accuracy of real side-scan sonar data and validates the feasibility of the proposed method. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

21 pages, 2281 KiB  
Article
Feature Extraction and Classification of Simulated Monostatic Acoustic Echoes from Spherical Targets of Various Materials Using Convolutional Neural Networks
by Bernice Kubicek, Ananya Sen Gupta and Ivars Kirsteins
J. Mar. Sci. Eng. 2023, 11(3), 571; https://doi.org/10.3390/jmse11030571 - 07 Mar 2023
Cited by 1 | Viewed by 1227
Abstract
Active sonar target classification remains an ongoing area of research due to the unique challenges associated with the problem (unknown target parameters, dynamic oceanic environment, different scattering mechanisms, etc.). Many feature extraction and classification techniques have been proposed, but there remains a need [...] Read more.
Active sonar target classification remains an ongoing area of research due to the unique challenges associated with the problem (unknown target parameters, dynamic oceanic environment, different scattering mechanisms, etc.). Many feature extraction and classification techniques have been proposed, but there remains a need to relate and explain the classifier results in the physical domain. This work examines convolutional neural networks trained on simulated data with a known ground truth projected onto two time-frequency representations (spectrograms and scalograms). The classifiers were trained to discriminate the target material type, geometry, and internal fluid filling, while the hyperparameters were tuned to the classification task using Bayesian optimization. The trained networks were examined using an explainable artificial intelligence technique, gradient-weighted class activation mapping, to uncover the informative features used in discrimination. This analysis resulted in visual representations that allowed the CNN choices to be related to the physical domain. It was found that the scalogram representation provided a negligible classification accuracy increase compared with the spectrograms. Networks trained to discriminate between target geometries resulted in the highest accuracy, and the networks trained to discriminate the internal fluid of the target resulted in the lowest accuracy. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

14 pages, 4115 KiB  
Article
A Hybrid–Source Ranging Method in Shallow Water Using Modal Dispersion Based on Deep Learning
by Tong Wang, Lin Su, Qunyan Ren, He Li, Yuqing Jia and Li Ma
J. Mar. Sci. Eng. 2023, 11(3), 561; https://doi.org/10.3390/jmse11030561 - 06 Mar 2023
Viewed by 977
Abstract
The relationship between modal elevation angle and the relative arrival time between modes, derived from exploiting modal dispersion, provides source information that is less susceptible to environmental influences. However, the standard method based on modal dispersion has limitations for application. To overcome this, [...] Read more.
The relationship between modal elevation angle and the relative arrival time between modes, derived from exploiting modal dispersion, provides source information that is less susceptible to environmental influences. However, the standard method based on modal dispersion has limitations for application. To overcome this, we propose a hybrid method for passive source ranging of low-frequency underwater acoustic-pulse signals in a range-independent shallow-water waveguide. Our method leverages deep learning, utilizing the intermediate results from the standard method as inputs, and short-time conventional beamforming to transform signals received by a vertical line array into a beam-time-domain sound-intensity map. The source range is estimated using an attention-based regression model with a ResNet backbone that has been trained on the beam-time-domain sound-intensity map. Our experimental results demonstrate the superiority of the proposed method, with a mean relative-error reduction of 71%, mean root-squared error reduction of 2.25 km, and an accuracy of 85%, compared to matched-field processing. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

32 pages, 10878 KiB  
Article
Categorizing Shallow Marine Soundscapes Using Explained Clusters
by Clea Parcerisas, Irene T. Roca, Dick Botteldooren, Paul Devos and Elisabeth Debusschere
J. Mar. Sci. Eng. 2023, 11(3), 550; https://doi.org/10.3390/jmse11030550 - 04 Mar 2023
Viewed by 1901
Abstract
Natural marine soundscapes are being threatened by increasing anthropic noise, particularly in shallow coastal waters. To preserve and monitor these soundscapes, understanding them is essential. Here, we propose a new method for semi-supervised categorization of shallow marine soundscapes, with further interpretation of these [...] Read more.
Natural marine soundscapes are being threatened by increasing anthropic noise, particularly in shallow coastal waters. To preserve and monitor these soundscapes, understanding them is essential. Here, we propose a new method for semi-supervised categorization of shallow marine soundscapes, with further interpretation of these categories according to concurrent environmental conditions. The proposed methodology uses a nonlinear mapping of short-term spectrograms to a two-dimensional space, followed by a density-based clustering algorithm to identify similar sound environments. A random forest classifier, based on additional environmental data, is used to predict their occurrence. Finally, explainable machine learning tools provide insight into the ecological explanation of the clusters. This methodology was tested in the Belgian part of the North Sea, and resulted in clearly identifiable categories of soundscapes that could be explained by spatial and temporal environmental parameters, such as distance to the shore, bathymetry, tide or season. Classifying soundscapes facilitates their identification, which can be useful for policy making or conservation programs. Soundscape categorization, as proposed in this work, could be used to monitor acoustic trends and patterns in space and time that might provide useful indicators of biodiversity and ecosystem functionality change. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

17 pages, 5473 KiB  
Article
A Lightweight Network Model Based on an Attention Mechanism for Ship-Radiated Noise Classification
by Shuang Yang, Lingzhi Xue, Xi Hong and Xiangyang Zeng
J. Mar. Sci. Eng. 2023, 11(2), 432; https://doi.org/10.3390/jmse11020432 - 16 Feb 2023
Cited by 9 | Viewed by 1530
Abstract
Recently, deep learning has been widely used in ship-radiated noise classification. To improve classification efficiency, avoiding high computational costs is an important research direction in ship-radiated noise classification. We propose a lightweight squeeze and excitation residual network 10 (LW-SEResNet10). In ablation experiments of [...] Read more.
Recently, deep learning has been widely used in ship-radiated noise classification. To improve classification efficiency, avoiding high computational costs is an important research direction in ship-radiated noise classification. We propose a lightweight squeeze and excitation residual network 10 (LW-SEResNet10). In ablation experiments of LW-SEResNet10, the use of ResNet10 instead of ResNet18 reduced 56.1% of parameters, while the accuracy is equivalent to ResNet18. The improved accuracy indicates that the ReLU6 enhanced the model stability, and an attention mechanism captured the channel dependence. The ReLU6 activation function does not introduce additional parameters, and the number of parameters introduced by the attention mechanism accounts for 0.2‰ of the model parameters. The 3D dynamic MFCC feature performs better than MFCC, Mel-spectrogram, 3D dynamic Mel-spectrogram, and CQT. Moreover, the LW-SEResNet10 model is also compared with ResNet and two classic lightweight models. The experimental results show that the proposed model achieves higher classification accuracy and is lightweight in terms of not only the model parameters, but also the time consumption. LW-SEResNet10 also outperforms the state-of-the-art model CRNN-9 by 3.1% and ResNet by 3.4% and has the same accuracy as AudioSet pretrained STM, which achieves the trade-off between accuracy and model efficiency. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

18 pages, 3421 KiB  
Article
Underwater Reverberation Suppression via Attention and Cepstrum Analysis-Guided Network
by Yukun Hao, Xiaojun Wu, Huiyuan Wang, Xinyi He, Chengpeng Hao, Zirui Wang and Qiao Hu
J. Mar. Sci. Eng. 2023, 11(2), 313; https://doi.org/10.3390/jmse11020313 - 01 Feb 2023
Cited by 2 | Viewed by 1620
Abstract
Active sonar systems are one of the most commonly used acoustic devices for underwater equipment. They use observed signals, which mainly include target echo signals and reverberation, to detect, track, and locate underwater targets. Reverberation is the primary background interference for active sonar [...] Read more.
Active sonar systems are one of the most commonly used acoustic devices for underwater equipment. They use observed signals, which mainly include target echo signals and reverberation, to detect, track, and locate underwater targets. Reverberation is the primary background interference for active sonar systems, especially in shallow sea environments. It is coupled with the target echo signal in both the time and frequency domain, which significantly complicates the extraction and analysis of the target echo signal. To combat the effect of reverberation, an attention and cepstrum analysis-guided network (ACANet) is proposed. The baseline system of the ACANet consists of a one-dimensional (1D) convolutional module and a reconstruction module. These are used to perform nonlinear mapping and to reconstruct clean spectrograms, respectively. Then, since most underwater targets contain multiple highlights, a cepstrum analysis module and a multi-head self-attention module are deployed before the baseline system to improve the reverberation suppression performance for multi-highlight targets. The systematic evaluation demonstrates that the proposed algorithm effectively suppresses the reverberation in observed signals and greatly preserves the highlight structure. Compared with NMF methods, the proposed ACANet no longer requires the target echo signal to be low-rank. Thus, it can better suppress the reverberation in multi-highlight observed signals. Furthermore, it demonstrates superior performance over NMF methods in the task of reverberation suppression for single-highlight observed signals. It creates favorable conditions for underwater platforms, such as unmanned underwater vehicles (UUVs), to carry out underwater target detection and tracking tasks. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

12 pages, 343 KiB  
Article
VFR: The Underwater Acoustic Target Recognition Using Cross-Domain Pre-Training with FBank Fusion Features
by Ji Wu, Peng Li, Yongxian Wang, Qiang Lan, Wenbin Xiao and Zhenghua Wang
J. Mar. Sci. Eng. 2023, 11(2), 263; https://doi.org/10.3390/jmse11020263 - 23 Jan 2023
Cited by 4 | Viewed by 1546
Abstract
Underwater acoustic target recognition is a hot research area in acoustic signal processing. With the development of deep learning, feature extraction and neural network computation have become two major steps of recognition. Due to the complexity of the marine environment, traditional feature extraction [...] Read more.
Underwater acoustic target recognition is a hot research area in acoustic signal processing. With the development of deep learning, feature extraction and neural network computation have become two major steps of recognition. Due to the complexity of the marine environment, traditional feature extraction cannot express the characteristics of the targets well. In this paper, we propose an underwater acoustic target recognition approach named VFR. VFR adopts a novel feature extraction method by fusing three-dimensional FBank features, and inputs the extracted features into a residual network, instead of the classical CNN network, plus cross-domain pre-training to perform target recognition. The experimental results show that VFR achieves 98.5% recognition accuracy on the randomly divided ShipsEar dataset and 93.8% on the time-divided dataset, respectively, which are better than state-of-the-art results. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

18 pages, 1341 KiB  
Article
Convolutional Autoencoding of Small Targets in the Littoral Sonar Acoustic Backscattering Domain
by Timothy J. Linhardt, Ananya Sen Gupta and Matthew Bays
J. Mar. Sci. Eng. 2023, 11(1), 21; https://doi.org/10.3390/jmse11010021 - 23 Dec 2022
Cited by 2 | Viewed by 1687
Abstract
Automated target recognition is an important task in the littoral warfare domain, as distinguishing mundane objects from mines can be a matter of life and death. This is initial work towards the application of convolutional autoencoding to the littoral sonar space, with goals [...] Read more.
Automated target recognition is an important task in the littoral warfare domain, as distinguishing mundane objects from mines can be a matter of life and death. This is initial work towards the application of convolutional autoencoding to the littoral sonar space, with goals of disentangling the reflection noise prevalent in underwater acoustics and allowing recognition of the shape and material of targets. The autoencoders were trained on magnitude Fourier transforms of the TREX13 dataset. Clusters in the encoding space representing the known variable of measurement distance between the target and the sensor were found. An encoding vector space of around 16 dimensions appeared sufficient, and the space was shown to generalize well to unseen data. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

15 pages, 40805 KiB  
Article
Experimental Study on the Target–Receiver Formation Problem with the Exploitation of Coherent and Non-Coherent Bearing Information
by Lu Wang, Shiliang Fang, Yixin Yang and Xionghou Liu
J. Mar. Sci. Eng. 2022, 10(12), 1922; https://doi.org/10.3390/jmse10121922 - 06 Dec 2022
Viewed by 997
Abstract
Localization of emitting sources is a fundamental task in sonar applications. One of the most important factors that affect the localization performance is the sensor–target geometry. The sensor formation problem is usually addressed in related work assuming that the target is static and [...] Read more.
Localization of emitting sources is a fundamental task in sonar applications. One of the most important factors that affect the localization performance is the sensor–target geometry. The sensor formation problem is usually addressed in related work assuming that the target is static and the location is known to a certain degree, but this is not the case for many underwater surveillance problems. In this paper, we deal with the target–receiver formation problem from a different perspective, and propose to investigate the effect of target–receiver geometry on localization performance by exploiting the spatial spectrum of the direct position determination (DPD) methods. For a given multi-array system, the transformation of geometrical patterns can be explicitly demonstrated as the target moves along the track. Meaningful characteristics of the DPD methods are obtained from the experimental results, where coherent and non-coherent bearing information is used and compared. The feasibility of the DPD approaches in the ocean environments is also investigated by comparing with a matched filter processing (MFP)-based multi-array processor in order to validate the credibility of the results in this paper. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

18 pages, 1238 KiB  
Article
Differential Evolution Algorithm-Aided Time-Varying Carrier Frequency Offset Estimation for OFDM Underwater Acoustic Communication
by Haijun Wang, Weihua Jiang, Qing Hu, Jianjun Zhang and Yanqing Jia
J. Mar. Sci. Eng. 2022, 10(12), 1826; https://doi.org/10.3390/jmse10121826 - 28 Nov 2022
Cited by 1 | Viewed by 1255
Abstract
Orthogonal frequency division multiplexing (OFDM) is the preferred scheme for high-speed communication in the field of underwater acoustic communication. However, it is very sensitive to the carrier frequency offset (CFO). This study used a time-varying CFO estimation method aided by the differential evolution [...] Read more.
Orthogonal frequency division multiplexing (OFDM) is the preferred scheme for high-speed communication in the field of underwater acoustic communication. However, it is very sensitive to the carrier frequency offset (CFO). This study used a time-varying CFO estimation method aided by the differential evolution (DE) algorithm to accurately estimate the CFO of an OFDM system. This method was based on the principle that the received OFDM signal with inter-carrier interference could be considered by a Multi Carrier-code division multiple access (MC-CDMA) system on the receiver side because MC-CDMA is a technology that combines OFDM and code division multiple access (CMDA). Because it is suitable for solving problems where there are dependencies between adjacent variables, the DE algorithm was used to capture the varying CFO values on the adjacent blocks. The spreading code of the MC-CDMA was obtained based on the estimated CFO values, which were elements in the DE solutions. Then the received signal was reconstructed. The Root-Mean-Square Error between the reconstructed and actual received signals was used as the cost function, and the CFO was estimated using the DE algorithm because of its powerful parallel search capability. The simulation results showed that the proposed method had a high estimation accuracy. Compared with other intelligent optimization algorithms such as the genetic algorithm and simulated annealing mutated-genetic algorithm, the time-varying CFO estimation performance of the DE algorithm was better because of its unique ability to solve problems with dependencies between adjacent variables. Specifically, under the condition of a high signal-to-noise ratio, the improvement of estimation accuracy reaches 36.13%, and the Bit Error Rate of demodulation is thus reduced by 75%, compared with the reference algorithms. In addition, the proposed method also has good applicability to modulation methods. For phase-shift keying and quadrature amplitude modulation, in particular, the proposed method not only achieved high-precision time-varying CFO estimation values, but also reduced the demodulation deterioration caused by noise. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

22 pages, 9768 KiB  
Article
Small-Sample Sonar Image Classification Based on Deep Learning
by Zezhou Dai, Hong Liang and Tong Duan
J. Mar. Sci. Eng. 2022, 10(12), 1820; https://doi.org/10.3390/jmse10121820 - 25 Nov 2022
Cited by 3 | Viewed by 2310
Abstract
Deep learning is a core technology for sonar image classification. However, owing to the cost of sampling, a lack of data for sonar image classification impedes the training and deployment of classifiers. Classic deep learning models such as AlexNet, VGG, GoogleNet, and ResNet [...] Read more.
Deep learning is a core technology for sonar image classification. However, owing to the cost of sampling, a lack of data for sonar image classification impedes the training and deployment of classifiers. Classic deep learning models such as AlexNet, VGG, GoogleNet, and ResNet suffer from low recognition rates and overfitting. This paper proposes a novel network (ResNet-ACW) based on a residual network and a combined few-shot strategy, which is derived from generative adversarial networks (GAN) and transfer learning (TL). We establish a sonar image dataset of six-category targets, which are formed by sidescan sonar, forward-looking sonar, and three-dimensional imaging sonar. The training process of ResNet-ACW on the sonar image dataset is more stable and the classification accuracy is also improved through an asymmetric convolution and a designed network structure. We design a novel GAN (LN-PGAN) that can generate images more efficiently to enhance our dataset and fine-tune ResNet-ACW pretrained on mini-ImageNet. Our method achieves 95.93% accuracy and a 14.19% increase in the six-category target sonar image classification tasks. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

25 pages, 4783 KiB  
Article
Performance Comparison of Feature Detectors on Various Layers of Underwater Acoustic Imagery
by Xiaoteng Zhou, Shihao Yuan, Changli Yu, Hongyuan Li and Xin Yuan
J. Mar. Sci. Eng. 2022, 10(11), 1601; https://doi.org/10.3390/jmse10111601 - 31 Oct 2022
Cited by 4 | Viewed by 1456
Abstract
Image feature matching is essential in many computer vision applications, and the foundation of matching is feature detection, which is a crucial feature quantification process. This manuscript focused on detecting more features from underwater acoustic imageries for further ocean engineering applications of autonomous [...] Read more.
Image feature matching is essential in many computer vision applications, and the foundation of matching is feature detection, which is a crucial feature quantification process. This manuscript focused on detecting more features from underwater acoustic imageries for further ocean engineering applications of autonomous underwater vehicles (AUVs). Currently, the mainstream feature detection operators are developed for optical images, and there is not yet a feature detector oriented to underwater acoustic imagery. To better analyze the suitability of existing feature detectors for acoustic imagery and develop an operator that can robustly detect feature points in underwater imageries in the future, this manuscript compared the performance of well-established handcrafted feature detectors and that of the increasingly popular deep-learning-based detectors to fill the gap in the literature. The datasets tested are from the most commonly used side-scan sonars (SSSs) and forward-looking sonars (FLSs). Additionally, the detection idea of these detectors on the acoustic imagery phase congruency (PC) layer was innovatively proposed with the aim of finding a solution that balances detection accuracy and speed. The experimental results show that the ORB (Oriented FAST and Rotated BRIEF) and BRISK (Binary Robust Invariant Scalable Keypoints) detectors achieve the best overall performance, the FAST detector is the fastest, and the PC and Sobel layers are the most favorable for implementing feature detection. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

24 pages, 3245 KiB  
Article
Combined LOFAR and DEMON Spectrums for Simultaneous Underwater Acoustic Object Counting and F0 Estimation
by Liming Li, Sanming Song and Xisheng Feng
J. Mar. Sci. Eng. 2022, 10(10), 1565; https://doi.org/10.3390/jmse10101565 - 21 Oct 2022
Cited by 4 | Viewed by 2552
Abstract
In a typical underwater acoustic target detection mission, we have to estimate the target number (N), perform source separation when N>1, and consequently predict the motion parameters such as fundamental frequency (F0) from separated noises [...] Read more.
In a typical underwater acoustic target detection mission, we have to estimate the target number (N), perform source separation when N>1, and consequently predict the motion parameters such as fundamental frequency (F0) from separated noises for each target. Although deep learning methods have been adopted in each task, their successes strongly depend on the feed-in features. In this paper, we evaluate several time-frequency features and propose a universal feature extraction strategy for object counting and F0 estimation simultaneously, with a convolutional recurrent neural network (CRNN) as the backbone. On one hand, LOFAR and DEMON are feasible for low-speed and high-speed analysis, respectively, and are combined (LOFAR + DEMON) to cope with full-condition estimation. On the other hand, a comb filter (COMB) is designed and applied to the combined spectrum for harmonicity enhancement, which will be further streamed into the CRNN for prediction. Experiments show that (1) in the F0 estimation task, feeding the filtered combined feature (LOFAR + DEMON + COMB) into the CRNN achieves an accuracy of 98% in the lake trial dataset, which is superior to LOFAR + COMB (83%) or DEMON + COMB (94%) alone, demonstrating that feature combination is plausible. (2) In a counting task, the prediction accuracy of the combined feature (LOFAR + DEMON, COMB included or excluded) is comparable to the state-of-the-art on simulation dataset and dominates the rest on the lake trial dataset, indicating that LOFAR + DEMON can be used as a common feature for both tasks. (3) The inclusion of COMB accelerates the convergence speed of the F0 estimation task, however, it penalizes the counting task by a depression of 13% on average, partly due to the merging effects brought in by the broadband filtering of COMB. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

24 pages, 7301 KiB  
Article
Predicting Acoustic Transmission Loss Uncertainty in Ocean Environments with Neural Networks
by Brandon M. Lee, Jay R. Johnson and David R. Dowling
J. Mar. Sci. Eng. 2022, 10(10), 1548; https://doi.org/10.3390/jmse10101548 - 20 Oct 2022
Cited by 4 | Viewed by 1633
Abstract
Computational predictions of acoustic transmission loss (TL) in ocean environments depend on the relevant environmental characteristics, such as the sound speed field, bathymetry, and seabed properties. When databases are used to obtain estimates of these properties, the resulting predictions of TL are uncertain, [...] Read more.
Computational predictions of acoustic transmission loss (TL) in ocean environments depend on the relevant environmental characteristics, such as the sound speed field, bathymetry, and seabed properties. When databases are used to obtain estimates of these properties, the resulting predictions of TL are uncertain, and this uncertainty can be quantified via the probability density function (PDF) of TL. A machine learning technique for quickly estimating the PDF of TL using only a single, baseline TL calculation is presented here. The technique shifts the computational burden from present-time Monte-Carlo (MC) TL simulations in the environment of interest to ahead-of-time training of a neural network using equivalent MC TL simulations in hundreds of ocean environments. An environmental uncertainty approach which draws information from global databases is also described and is used to create hundreds of thousands of TL-field examples across 300 unique ocean environments at ranges up to 100 km for source frequencies between 50 and 600 Hz. A subset of the total dataset is used to train and compare neural networks with various architectures and TL-PDF-generation methods. Finally, the remaining dataset examples are used to compare the machine-learning technique’s accuracy and computational effort to that of prior TL-uncertainty-estimation techniques. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

14 pages, 1183 KiB  
Article
STM: Spectrogram Transformer Model for Underwater Acoustic Target Recognition
by Peng Li, Ji Wu, Yongxian Wang, Qiang Lan and Wenbin Xiao
J. Mar. Sci. Eng. 2022, 10(10), 1428; https://doi.org/10.3390/jmse10101428 - 04 Oct 2022
Cited by 16 | Viewed by 2525
Abstract
With the evolution of machine learning and deep learning, more and more researchers have utilized these methods in the field of underwater acoustic target recognition. In these studies, convolutional neural networks (CNNs) are the main components of recognition models. In recent years, a [...] Read more.
With the evolution of machine learning and deep learning, more and more researchers have utilized these methods in the field of underwater acoustic target recognition. In these studies, convolutional neural networks (CNNs) are the main components of recognition models. In recent years, a neural network model Transformer that uses a self-attention mechanism was proposed and achieved good performance in deep learning. In this paper, we propose a Transformer-based underwater acoustic target recognition model STM. To the best of our knowledge, this is the first work to introduce Transformer into the underwater acoustic field. We compared the performance of STM with CNN, ResNet18, and other multi-class algorithm models. Experimental results illustrate that under two commonly used dataset partitioning methods, STM achieves 97.7% and 89.9% recognition accuracy, respectively, which are 13.7% and 50% higher than the CNN Model. STM also outperforms the state-of-the-art model CRNN-9 by 3.1% and ResNet18 by 1.8%. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

21 pages, 8316 KiB  
Article
A Novel Acoustic Method for Cavitation Identification of Propeller
by Yang Li and Lilin Cui
J. Mar. Sci. Eng. 2022, 10(9), 1225; https://doi.org/10.3390/jmse10091225 - 01 Sep 2022
Cited by 3 | Viewed by 1485
Abstract
When a propeller is under a state of cavitation, it will experience negative effects, including strong noise, vibration, and even damage to the blades. Accordingly, the detection of propeller cavitation has attracted the attention of researchers. Propeller noise signal contains a wealth of [...] Read more.
When a propeller is under a state of cavitation, it will experience negative effects, including strong noise, vibration, and even damage to the blades. Accordingly, the detection of propeller cavitation has attracted the attention of researchers. Propeller noise signal contains a wealth of cavitation information, which is a powerful method to identify the cavitation state. Considering the nonlinear characteristics of propeller noise, a feature describing the complexity of nonlinear signals, which is called refined composite multiscale fluctuation-based dispersion entropy (RCMFDE), is adopted as the indicator of propeller cavitation, and a framework for the identification of propeller cavitation state is established in this paper. Firstly, the propeller noise signal is decomposed by the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method, and the intrinsic mode function (IMF) components with cavitation characteristics are extracted. Secondly, the RCMFDE of the IMF components is computed. Finally, a hybrid optimization support vector machine (SVM) is established to classify the features, in which a Relief-F filter is utilized to reduce the feature dimension, and a particle swarm optimization (PSO) wrapper is utilized to optimize the parameters of the SVM. The experimental results demonstrate encouraging accuracy to apply this approach to identify the propeller cavitation states, with an identification accuracy of 91.11%. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

18 pages, 2979 KiB  
Article
Study on Small Samples Active Sonar Target Recognition Based on Deep Learning
by Yule Chen, Hong Liang and Shuo Pang
J. Mar. Sci. Eng. 2022, 10(8), 1144; https://doi.org/10.3390/jmse10081144 - 19 Aug 2022
Cited by 7 | Viewed by 2206
Abstract
Underwater target classification methods based on deep learning suffer from obvious model overfitting and low recognition accuracy in the case of small samples and complex underwater environments. This paper proposes a novel classification network (EfficientNet-S) based on EfficientNet-V2S. After optimization with model scaling, [...] Read more.
Underwater target classification methods based on deep learning suffer from obvious model overfitting and low recognition accuracy in the case of small samples and complex underwater environments. This paper proposes a novel classification network (EfficientNet-S) based on EfficientNet-V2S. After optimization with model scaling, EfficientNet-S significantly improves the recognition accuracy of the test set. As deep learning models typically require very large datasets to train millions of model parameter, the number of underwater target echo samples is far more insufficient. We propose a deep convolutional generative adversarial network (SGAN) based on the idea of group padding and even-size convolution kernel for high-quality data augmentation. The results of anechoic pool experiments show that our algorithm effectively suppresses the overfitting phenomenon, achieves the best recognition accuracy of 92.5%, and accurately classifies underwater targets based on active echo datasets with small samples. Full article
(This article belongs to the Special Issue Application of Sensing and Machine Learning to Underwater Acoustic)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-17
Back to TopTop